Xiaomi: MiMo-V2.5
xiaomi/mimo-v2.5
MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perception across image and video understanding...
Prompt $/1M
$0.140
Completion $/1M
$0.280
Context
1,048,576 tok
Best provider
47 tok/s · Venice
Specs
- Model id
- xiaomi/mimo-v2.5
- Display name
- Xiaomi: MiMo-V2.5
- Modality
- text+image+audio+video->text
- Tokenizer
- Other
- Instruct type
- —
- Context length
- 1,048,576
- Max completion
- 131,072
- Prompt $/1M
- $0.140
- Completion $/1M
- $0.280
- Free tier
- no
Capabilities
- Function callingno
- JSON modeno
- System promptno
- Visionyes
- Moderatedno
Benchmark scores
Each axis is one benchmark, normalized to the best model in the field.
No benchmark data for this model.
Speed by provider
| Provider | tok/s |
|---|---|
| Venicefastest | 47 |
| Xiaomi | 32 |
| Novita | 32 |
| DeepInfra | 32 |
| GMICloud | 23 |
| Parasail | 22 |
| DigitalOcean | 15 |